請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74402
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 許聿廷(Yu-Ting Hsu) | |
dc.contributor.author | Zhi -Xun Xu | en |
dc.contributor.author | 許智勛 | zh_TW |
dc.date.accessioned | 2021-06-17T08:33:51Z | - |
dc.date.available | 2020-08-28 | |
dc.date.copyright | 2019-08-28 | |
dc.date.issued | 2019 | |
dc.date.submitted | 2019-08-09 | |
dc.identifier.citation | Adler, J. L., Satapathy, G., Manikonda, V., Bowles, B., and Blue, V. J. (2005). A multi-agent approach to cooperative traffic management and route guidance. Transportation Research Part B: Methodological, 39(4), 297-318
Chang, T.-H., and Sun, G.-Y. (2004). Modeling and optimization of an oversaturated signalized network. Transportation Research Part B: Methodological, 38(8), 687-707 Dimitriou, L., Tsekeris, T., and Stathopoulos, A. (2008). Adaptive hybrid fuzzy rule-based system approach for modeling and predicting urban traffic flow. Transportation Research Part C: Emerging Technologies, 16(5), 554-573 Dougherty, M. (1995). A review of neural networks applied to transport. Transportation Research Part C: Emerging Technologies, 3(4), 247-260 Elman, J. L. (1990). Finding Structure in Time. Cognitive Science, 14(2), 179-211 Frank, R. J., Davey, N., and Hunt, S. P. (2001). Time Series Prediction and Neural Networks. Journal of Intelligent and Robotic Systems, 31(1), 91-103 Guardiola, I. G., Leon, T., and Mallor, F. (2014). A functional approach to monitor and recognize patterns of daily traffic profiles. Transportation Research Part B: Methodological, 65, 119-136 Hochreiter, S., and Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780 Kang, D., Lv, Y., and Chen, Y. (2017, 16-19 Oct. 2017). Short-term traffic flow prediction with LSTM recurrent neural network. Paper presented at the 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC). Mucsi, K., Khan, A. M., and Ahmadi, M. (2011). An Adaptive Neuro-Fuzzy Inference System for estimating the number of vehicles for queue management at signalized intersections. Transportation Research Part C: Emerging Technologies, 19(6), 1033-1047 Nair, V., and Hinton, G. E. (2010). Rectified linear units improve restricted boltzmann machines. Paper presented at the Proceedings of the 27th International Conference on International Conference on Machine Learning, Haifa, Israel. Okutani, I., and Stephanedes, Y. J. (1984). Dynamic prediction of traffic volume through Kalman filtering theory. Transportation Research Part B: Methodological, 18(1), 1-11 Ozan, C., Baskan, O., Haldenbilen, S., and Ceylan, H. (2015). A modified reinforcement learning algorithm for solving coordinated signalized networks. Transportation Research Part C: Emerging Technologies, 54, 40-55 Papola, N., and Fusco, G. (1998). Maximal bandwidth problems: a new algorithm based on the properties of periodicity of the system. Transportation Research Part B: Methodological, 32(4), 277-288 Polson, N. G., and Sokolov, V. O. (2017). Deep learning for short-term traffic flow prediction. Transportation Research Part C: Emerging Technologies, 79, 1-17 Rosenblatt, F. (1958). The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65(6), 386-408 Teodorović, D., Varadarajan, V., Popović, J., Chinnaswamy, M. R., and Ramaraj, S. (2006). Dynamic programming—neural network real-time traffic adaptive signal control algorithm. Annals of Operations Research, 143(1), 123-131 Vlahogianni, E. I., Karlaftis, M. G., and Golias, J. C. (2014). Short-term traffic forecasting: Where we are and where we’re going. Transportation Research Part C: Emerging Technologies, 43, 3-19 Yaqin, W., Yue, C., Minggui, Q., and Yangyong, Z. (2006, 21-23 June 2006). Dynamic Traffic Prediction Based on Traffic Flow Mining. Paper presented at the 2006 6th World Congress on Intelligent Control and Automation. Yin, Y. (2008). Robust optimal traffic signal timing. Transportation Research Part B: Methodological, 42(10), 911-924 Chang, Z. H. (2002). 應用智慧型號誌控制器執行適應性控制之研究. (碩士). 國立臺灣大學, 台北市. Chen, N. Q. (2008). K-means集群分析法應用於號誌定時時制時段劃分之研究. (碩士). 逢甲大學, 台中市. Hsu, S. X. (2011). 混合車流之過飽和路段號誌最佳化模式研究 = A study of mixed traffic signal optimal model on oversaturated section: 碩士論文--國立臺灣大學土木工程學研究所. Hu, S. R., and Cai, D. C. (2016). 應用格位傳遞與轉向比估計模式於適應性號誌控制邏輯之構建. [Applying the Cell Transmission and Turning Proportion Estimation Models for the Development of an Adaptive Signal Control Logic]. 運輸學刊, 28(1), 35-81 Lin, L. T. (1999). 以續進為目標之號誌群組間時差連鎖設計. Lin, L. T., Huang, H. Y., and Huang, Q. C. (2012). 幹道系統延滯最小下續進路口數最大化模式之研究. [A Model for Maximum Progression under Minimum Delay along an Urban Arterial]. 運輸學刊, 24(4), 529-554 Lin, L. T., Xie, C. M., and Gu, X. Q. (2010). 高飽和下幹道號誌系統續進路口數最大化模式. [A Model for Maximum Progressive Intersections on Signalized Arterial Systems under High Saturated Conditions]. 中國土木水利工程學刊, 22(3), 319-331 Lin, L. T., Yang, J. X., and Huang, H. R. (2001). 以續進最大化為主延滯最小化為輔之程序性群組間時差設計. [Sequential Offset Design on Signal Subnet Work Interfaces with Minimum Delay Considerations Based on Maximum Progressions]. 運輸計劃季刊, 30(4), 795-822 Liu, X. H. (2013). 混合車流等候結構之號誌分流最佳化模式. (碩士). 國立臺灣大學, 台北市. Wu, Y. C. (2011). 幹道群組適應性號誌控制模式之開發研究. 成功大學, Xu, G. J. (2003). 構建自學式適應性交通號誌控制模式之研究. (博士). 國立成功大學, 台南市. Zhang, T. X., and Yang, L. K. (2011). 以延滯指標評估幾種交通號誌控制邏輯之適用時機-以獨立路口為例. [Evaluation of Preferred Applications of Traffic Signal Algorithms Using Traffic Delay Index for an Isolated Intersection]. 運輸學刊, 23(1), 61-96 Zhu, S. W. (1991). 適應性號誌邏輯之微觀分析. (碩士). 國立臺灣大學, 台北市. 蔡輝昇, 邱大恭 (1987)。以數學規劃模式求解獨立交叉路口號誌時制計畫。運輸計劃季刊,第16卷第3期,PP.485-496。 蔡輝昇, 王國材 (1989)。發展T7F-T88求解幹道及網路號誌時制之理論及應用。運輸計劃季刊,第18卷第3期,PP. 277-301。 林良泰, 李建昌, 許乃文 (2001)。延滯最小化之幹道號誌時制設計研究。國際道路交通安全與執法研討會。 交通部運輸研究所 (2012)。運輸政策白皮書。 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74402 | - |
dc.description.abstract | 在每日上下班的尖峰時段,市區幹道總是充斥著壅塞造成大量的時間成本與燃油消耗,而經過周詳設計的號誌控制則可以有效的緩解壅塞。近年來,由於電腦計算資源的改善,透過即時運算來優化號誌控制,進而實現動態交通控制的相關研究如火如荼的進行。然而,在優化號誌的過程中,建構一個符合當地交通特性的代表模型,需要校估大量的參數,這過程是相當複雜且繁瑣的。另外,針對每個不同的交通情境,需在有限時間內求解有效率的交通控制策略,這對於實現動態號誌控制又是另一個棘手的問題。目前,在幹道層級的動態號誌控制的整體決策上,所需的計算量仍是相當大的,導致需要較多的運算時間。因此,在實務中,透過蒐集即時交通資訊,進而調整相對應的號誌控制策略仍然是相當富有挑戰性。有鑑於上述提及實現動態號誌控制的兩個主要限制,本研究利用已蒐集的大量歷史車流資料與交通號誌控制參數,在巨觀的觀點下,應用類神經網路,自動且有效率的架構出符合當地交通特性的代表模型與校估模型中的大量參數。更重要的是,本研究提出一套分解流程,將類神經網路所辨識且紀錄於其中的樣態逐一分解,用以架構號誌最佳化模式。此方法能顯著的改善求解號誌控制策略所需的時間,進而實現動態號誌控制。此外,一個預測短期交通流量的類神經網路模型也被建立,用以更新即時車流資訊,制定適當的動態號誌控制策略。本文的案例研究為連結國道一號高速公路的幹道。由於國道車流與幹道車流分屬不同道路層級,兩股巨大車流不斷匯聚導致頻繁的煞停,且車流量的即時變動性高,都可能是造成壅塞的原因。動態號誌控制依據即時車流資訊,及時且不斷的調整策略,以促進幹道車流有效續進,使匯聚後的大量車流能盡速紓解,這說明了其具備足夠的效益。透過案例研究的結果,說明本研究所提出的動態號誌控制策略,具備可行性與維持幹道續進的穩健性,也進而凸顯出動態號誌控制所具備的彈性調整優勢。整體來說,本研究所提出的動態號誌控制策略能迅速的挖掘巨量的歷史資料中所蘊含的交通樣態資訊,用以架構交通代表模型,並即時優化號誌策略。期望能提供實務上,一套自動且有效率的動態號誌控制策略之決策程序,以促進交通管理的效率。此外,本研究方法亦可進一步延伸,由類神經網路自行發展適應性號誌控制邏輯,具備研究潛力。 | zh_TW |
dc.description.abstract | In peak hours, congestion on urban roads leads to considerable extra time cost and fuel consumption. A well-designed signal control strategy can efficiently relieve congestion. Due to the improvement of computing resource, realizing dynamic signal control strategy becomes possible. However, estimating several traffic parameters to construct a model fitting real traffic conditions can be intricate, and solving the efficient signal control strategy in finite time also introduces another methodological difficulty. Currently, the solution time for determining a signal control strategy at an arterial road level can be still long. Hence, the concept of adjusting the control strategy based on the real-time traffic state is challenging in practice. This study applies the ANN model to construct a model fitting real traffic conditions and estimate a considerable number of parameters efficiently and automatically. Most importantly, a decomposition method is proposed in this research to decompose the patterns recorded in the ANN model and construct a signal optimization model, thereby improving the computational time of a signal control strategy significantly. A traffic demand prediction model is also developed to complete a dynamic signal control procedure. The arterial road connected with the Freeway No.1 of Taiwan is selected for the case study, which is an arterial road of great traffic volumes and complex flow merging and weaving, causing frequent occurrence of serious congestion. The results of the case study show the feasibility and robustness of the proposed approach to promote progression and highlight the advantage of adjusting the control strategy in a more dynamic manner. The proposed dynamic signal control strategy is expected to maximize the use of the historical traffic data and provide a credible and dynamic adjustment signal control module to relieve or even prevent congestion. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T08:33:51Z (GMT). No. of bitstreams: 1 ntu-108-R06521512-1.pdf: 2574554 bytes, checksum: 017f2f0d77323029c3fc6389f75a7c6b (MD5) Previous issue date: 2019 | en |
dc.description.tableofcontents | 中文摘要 I
ABSTRACT III TABLE OF CONTENTS V LIST OF FIGURES VIII LIST OF TABLES XIII CHAPTER 1 INTRODUTION 1 1.1 Research Background 1 1.2 Research Motivation 5 1.3 Research Objectives 7 1.4 Research Flowchart and Thesis Organization 8 CHAPTER 2 LITERATURE REVIEW 10 2.1 Signal Control Development in Taiwan 10 2.2 Dynamic Signal Control Strategies 12 2.3 Adaptive Signal Control Strategies 14 2.4 Traffic Pattern Recognition 16 2.5 Summary of the Literature Review 18 CHAPTER 3 METHODOLOGY 21 3.1 Predict Traffic Demand 23 3.1.1 Model Selection of Predicting Traffic Demand 23 3.1.2 VD Data Resolution and Time Step of the LSTM Model 24 3.1.3 Rolling Horizon Method Estimating Short-term Traffic Demand 24 3.2 Recognizing Patterns between VD Data and Signal Control Parameters 25 3.2.1 Model Selection of Recognizing Traffic Patterns 27 3.2.2 The Input and Output of the ANN Model 27 3.2.3 The Activation Function of the ANN Model 28 3.2.4 Limitation and Assumption of the ANN Model Method 29 3.3 Solving the Optimal Signal Control Strategy 30 3.3.1 Decomposition Method 31 3.3.2 Constructing the Signal Optimization Model 33 3.4 The Procedure of the Dynamic Signal Control Strategy 43 CHAPTER 4 CASE STUDY 46 4.1 The Information of the Collected Traffic Data 47 4.1.1 Preprocess the VD Data 47 4.1.2 Estimate the Missing Traffic Volume Data 48 4.1.3 Select the Period of Implementing Dynamic Signal Control Strategy 50 4.2 The Setting of the Models in Signal Optimization Procedure 51 4.2.1 The ANN Model 51 4.2.2 The LSTM Model 54 4.2.3 The Signal Optimization Model 57 4.3 Verify the Performance of the Developed Dynamic Signal Control Strategy 58 4.4 Summarize the Objectives of the Case Study 60 CHAPTER 5 RESULT AND DATA ANALYSIS 62 5.1 The Results of Recognizing Traffic Patterns 62 5.1.1 The Fitting Accuracy of the ANN Model 62 5.1.2 Improve the Prediction Accuracy of the ANN Model 65 5.1.3 The Summary of Recognizing Traffic Pattern by the ANN Model 80 5.2 The Results of Predicting Traffic Demand 80 5.2.1 The Results of the LSTM Model 81 5.2.2 The Performance of the Rolling Horizon Method 88 5.2.3 The Summary of Predicting Traffic Demand 96 5.3 The Results of Solving the Signal Optimization Model 96 5.3.1 The Solved Signal Control Strategy 98 5.3.2 The Solving Time of the Signal Optimization Model 104 5.3.3 The Summary of Solving the Signal Optimization Model 108 5.4 Examine the Solved Signal Control Strategy in Simulation Environment 111 5.4.1 Estimate the Simulation Model 112 5.4.2 The Testing Results of the Solved Signal Control Strategy 118 5.4.3 The Summary of the Simulation Examination in Vissim 132 5.5 Discussion 133 CHAPTER 6 CONCLUSION AND FUTURE WORK 135 6.1 Conclusions 136 6.2 Limitations 139 6.3 Future Work 141 REFERENCES 143 | |
dc.language.iso | en | |
dc.title | 基於類神經網路方法之最大化幹道續進動態號誌控制策略 | zh_TW |
dc.title | A Dynamic Signal Control Strategy to Maximize the Progression on an Arterial Road: A Neural Network Approach | en |
dc.type | Thesis | |
dc.date.schoolyear | 107-2 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 陳柏華(Albert Chen) | |
dc.contributor.oralexamcommittee | 胡守任(Shou-Ren Hu) | |
dc.subject.keyword | 動態號誌控制,類神經網路模型,幹道續進,交通需求預測,交通管理, | zh_TW |
dc.subject.keyword | Dynamic signal control,Neural network model,Arterial road progression,Traffic demand prediction,Traffic management, | en |
dc.relation.page | 147 | |
dc.identifier.doi | 10.6342/NTU201902935 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2019-08-12 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 土木工程學研究所 | zh_TW |
顯示於系所單位: | 土木工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-108-1.pdf 目前未授權公開取用 | 2.51 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。